Method, device and equipment for defecting and classifying steel sheet defects, and computer readable medium

A defect detection and classification method technology, applied in computer parts, calculation, program control design, etc., to achieve the effect of standardization and improvement

Inactive Publication Date: 2018-06-29
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF4 Cites 51 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Embodiments of the present invention provide a steel plate defect detection and classification method, device, equipment and computer readable medium to solve or alleviate the above technical problems in the prior art

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method, device and equipment for defecting and classifying steel sheet defects, and computer readable medium
  • Method, device and equipment for defecting and classifying steel sheet defects, and computer readable medium
  • Method, device and equipment for defecting and classifying steel sheet defects, and computer readable medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] see figure 1 , which is a flow chart of the steps of the steel plate defect detection and classification method according to Embodiment 1 of the present invention. The first embodiment provides a steel plate defect detection and classification method, including the following steps:

[0068] S110: Receive steel plate image data to be detected, and generate a detection request for steel plate defects.

[0069] When it is necessary to detect the surface defect of the steel plate, the image of the steel plate surface can be collected first, for example, it can be collected by equipment such as a camera. Then, after the image information of the corresponding steel plate is collected, a detection request is generated to detect surface defects of the steel plate.

[0070] S120: Send the steel plate picture data and the detection request to the optimal server equipped with the detection model according to the load balancing and scheduling strategy.

[0071] Before sending th...

Embodiment 2

[0081] The difference from Embodiment 1 is that this Embodiment 2 also updates the detection model on the basis of Embodiment 1. The specific scheme is as follows:

[0082] see Figure 4 , which is a flow chart of the steps of the method for detecting and classifying steel plate defects in the second embodiment. Embodiment 2 provides a steel plate defect detection and classification method, including the following steps:

[0083] S210: Receive steel plate image data to be detected, and generate a detection request for steel plate defects.

[0084] S220: Send the steel plate picture data and the detection request to the best server equipped with the detection model according to the load balancing and scheduling strategy.

[0085] S230: Receive a prediction result output after the detection model predicts and calculates the steel plate image data, and the prediction result includes the type of the steel plate defect.

[0086] S240: Execute a corresponding response action acco...

Embodiment 3

[0091] see Figure 5 , which is a flow chart of the steps of the method for detecting and classifying steel plate defects in the third embodiment. Embodiment 3 provides a steel plate defect detection and classification method, including the following steps:

[0092] S310: Receive steel plate picture data and a steel plate defect detection request.

[0093] S320: Carry out prediction calculation of steel plate defect on the image data of the steel plate through the detection model and output the prediction result, the prediction result includes the category of the steel plate defect.

[0094] Wherein, the detection model includes: a deep convolutional neural network and a defect location and classification network.

[0095] The deep convolutional neural network is used to extract the features of the steel plate picture, and the features are input into the defect location and classification network.

[0096] The defect location and classification network is used to judge whet...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a method for defecting and classifying steel sheet defects. The method comprises the following steps of receiving the image data of a to-be-detected steel sheet, and generatinga detecting request for the steel sheet defects; according to a load balancing and dispatching strategy, sending the image data of the steel sheet and the detecting request to an optimum server carrying a detection model; receiving a predicting result which is outputted by the detection model predicting and calculating the image data of the steel sheet, wherein the predicting result comprises thesteel sheet defect type; according to the predicting result outputted by the detection model, executing the applicable response action. The method provided by the embodiment has the advantages that bydetecting and judging the acquired steel sheet images in real time, the location and type of the steel sheet defect are obtained; furthermore, the detection model is iterated and upgraded, so that the detection model is suitable for meeting the latest requirements of production environment, and the industrial production line is obviously improved at the aspects of classifying accuracy, extendibility, normalization and the like.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a steel plate defect detection and classification method, device, equipment and computer readable medium. Background technique [0002] In the steel plate production scenario of the steel manufacturing industry, quality inspection is a key link in the production process. In the production environment of traditional iron and steel enterprises, an important means of quality control is to detect the surface state of the steel plate to determine whether there are flaws and defects in the steel plate, and to deal with the steel plate accordingly according to the test results. In the steel plate production line, this kind of quality inspection based on the surface state of the steel plate is mostly manual inspection or semi-automatic optical instrument-assisted quality inspection, which is not only inefficient, but also prone to misjudgment. In addition, the ind...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06K9/62G06F9/50
CPCG06F9/5083G06T7/0004G06T2207/20081G06T2207/20084G06F18/24
Inventor 冷家冰刘明浩梁阳文亚伟张发恩郭江亮唐进尹世明
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap